ggml-org/gguf-my-repo · Discussions

#171 opened 19 days ago by

King-Cane

Imatrix quantization option is giving txt format error

#170 opened 22 days ago by

kaetemi

[Errno 2] No such file: `llama-quantize`

👍 9

#167 opened about 2 months ago by

AlirezaF138

Failed to convert my repo to gguf

#166 opened about 2 months ago by

jonACE

The model downloaded from civiti only has safetytenser but no config. What should I do?

#165 opened about 2 months ago by

ly131022

getting "You must be logged in to use GGUF-my-repo" but I am logged in?

👍 2

#164 opened about 2 months ago by

diegoasua

Problem logging into gguf-my-repo although being logged in to hugging face

#163 opened about 2 months ago by

ulizilles

I have just converted Mistral-Small-3.1-24B-Instruct-2503 but it does not contain the vision adapter?

➕ 1

#160 opened 2 months ago by

Blakus

Invalid file type Error

👍 2

7

#158 opened 2 months ago by

Yuma42

SmolVLM2 Support

#156 opened 3 months ago by

PlayAI

ggml-org/gguf-my-repo fails to build

#153 opened 3 months ago by

lefromage

More storage

#151 opened 3 months ago by

noNyve

Cant convert Linq-Embed-Mistral

#150 opened 3 months ago by

Hoshino-Yumetsuki

Add IQ2_(some-letter) quantization

#149 opened 3 months ago by

noNyve

No support for making GGUF of HuggingFaceTB/SmolVLM-500M-Instruct

#148 opened 4 months ago by

TimexPeachtree

Unable to convert Senqiao/LISA_Plus_7b

#147 opened 4 months ago by

PlayAI

Unable to convert ostris/Flex.1-alpha

#146 opened 4 months ago by

fullsoftwares

Crashes on watt-ai/watt-tool-70B

#145 opened 4 months ago by

ejschwartz

Update app.py

#144 opened 5 months ago by

gghfez

Unable to convert Phi-3 Vision

➕ 2

#143 opened 5 months ago by

venkatsriram

Phi-4

#142 opened 5 months ago by

attashe

Accessing own private repos

#141 opened 6 months ago by

themex1380

Why can't i login?

#139 opened 6 months ago by

safe049

If generating model cards readmes, consider adding support for these extra authorship parameters

#137 opened 6 months ago by

mofosyne

Add F16 and BF16 quantization

#129 opened 7 months ago by

andito

update readme for card generation

4

#128 opened 7 months ago by

ariG23498

[bug] asymmetric t5 models fail to quantize

#126 opened 8 months ago by

pszemraj

[Bug] Extra files with related name were uploaded to the resulting repository

#125 opened 8 months ago by

Felladrin

Issue converting PEFT LoRA fine tuned model to GGUF

#124 opened 8 months ago by

AdnanRiaz107

Issue converting nvidia/NV-Embed-v2 to GGUF

#123 opened 8 months ago by

redshiva

Issue converting FLUX.1-dev model to GGUF format

5

#122 opened 8 months ago by

cbrescia

Add Llama 3.1 license

#121 opened 9 months ago by

jxtngx

Add an option to put all quantization variants in the same repo

#120 opened 9 months ago by

A2va

Phi-3.5-MoE-instruct

#117 opened 9 months ago by

goodasdgood

Fails to quntize T5 (xl and xxl) models

#116 opened 9 months ago by

girishponkiya

Arm optimized quants

➕ 3

#113 opened 9 months ago by

SaisExperiments

DeepseekForCausalLM is not supported

#112 opened 9 months ago by

nanowell

Please, update converting script. Llama.cpp added support for Nemotron and Minitron architectures.

#111 opened 9 months ago by

NikolayKozloff

Enable the created name repo to be without the quantization type

#110 opened 9 months ago by

A2va

I think I broke the space quantizing 4bit modle with Q4L

#106 opened 10 months ago by

hellork

Authorship Metadata support added to converter script, you may want to add the ability to add metadata overrides

#104 opened 10 months ago by

mofosyne

Please support this method:

➕ 2

7

#96 opened 11 months ago by

ZeroWw

Support Q2 imatrix quants

👍 5

#95 opened 11 months ago by

Dampfinchen

Maybe impose a max model size?